The analysis of human behavior by vision is a strong studied research topic. Indeed despite the progress brought by deep learning in computer vision, understanding finely what is happening in a scene is a task far from being solved because it presents a very high semantic level.In this thesis we focus on two applications: the recognition of temporally long activities in videos and the detection of interaction in images.The first contribution of this work is the development of the first database of daily activities with high intra-class variability.The second contribution is the proposal of a new method for interaction detection in a single shot on the image which allows it to be much faster than the state of the art two-step methods which a...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
International audienceThis paper describes a novel methodology for automated recognition of high-lev...
We present a system for the temporal detection of social interactions. Many of the works until now h...
With the massive increase of video content on Internet and beyond, the automatic understanding of vi...
The recognition and prediction of people activities from videos are major concerns in the field of c...
The main objective of the thesis is to propose a complete framework for the automatic activity disco...
Dans cette thèse nous étudions la reconnaissance d'actions humaines. Typiquement, différentes action...
The recognition and prediction of people activities from videos are major concerns in the field of c...
La reconnaissance du comportement et la prédiction des activités des personnes depuis la vidéo sont ...
This thesis focuses on the problem of understanding visual contents, which can be images, videos or ...
The literature in human activity recognition is very broad and many different approaches have been p...
La reconnaissance du comportement et la prédiction des activités des personnes depuis la vidéo sont ...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
International audienceThis paper describes a novel methodology for automated recognition of high-lev...
We present a system for the temporal detection of social interactions. Many of the works until now h...
With the massive increase of video content on Internet and beyond, the automatic understanding of vi...
The recognition and prediction of people activities from videos are major concerns in the field of c...
The main objective of the thesis is to propose a complete framework for the automatic activity disco...
Dans cette thèse nous étudions la reconnaissance d'actions humaines. Typiquement, différentes action...
The recognition and prediction of people activities from videos are major concerns in the field of c...
La reconnaissance du comportement et la prédiction des activités des personnes depuis la vidéo sont ...
This thesis focuses on the problem of understanding visual contents, which can be images, videos or ...
The literature in human activity recognition is very broad and many different approaches have been p...
La reconnaissance du comportement et la prédiction des activités des personnes depuis la vidéo sont ...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
Many videos depict people, and it is their interactions that inform us of their activities, relation...
International audienceThis paper describes a novel methodology for automated recognition of high-lev...
We present a system for the temporal detection of social interactions. Many of the works until now h...